© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 6368
    Prev
    Next
    INDEX
    Explanations

    gl

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WH
    -0.08
     WH
    -0.08
    .bottom
    -0.08
    IFY
    -0.08
     আট
    -0.08
     tet
    -0.07
    WM
    -0.07
     Oklahoma
    -0.07
     differentiated
    -0.07
    _WH
    -0.07
    POSITIVE LOGITS
    uc
    0.12
    Vectors
    0.08
    ancas
    0.08
     Drap
    0.08
    rap
    0.08
    vect
    0.08
    舰
    0.08
     Modules
    0.08
    _vectors
    0.07
    _Vector
    0.07
    Activations Density 0.001%

    No Known Activations